📄 Papers×1 mentions
Line
“We introduce LINE, a novel, training-free iterative approach tailored for open-vocabulary concept labeling in vision models.”
paper: LINE: Iterative LLM-based Neuron Explanation for Vision Models — 2026-04-10
What the smart people are recommending. 7865 books, tools, and products endorsed by the thinkers absorb.md tracks. Ranked by how many times each has been recommended across compiled podcasts, papers, posts, and tweets.
“We introduce LINE, a novel, training-free iterative approach tailored for open-vocabulary concept labeling in vision models.”
“we study the applicability of Conditional Neural Processes (CNP) to the task of self-supervised multimodal action prediction in robotics.”
“To address this, we propose OVS-DINO, a novel framework that revitalizes latent edge-sensitivity of DINO through structural alignment with the Segment Anything Model (SAM).”
“First, we release MiniF2F-Hard and FIMO-Hard, expert-reannotated Hard Mode variants of two widely-used ATP benchmarks.”
“We introduce InstAP, an Instance-Aware Pre-training framework that jointly optimizes global vision-text alignment and fine-grained, instance-level contrastive alignment by grounding textual mentions t…”
“Second, to address this gap, we introduce Phantasia, a context-adaptive backdoor attack that dynamically aligns its poisoned outputs with the semantics of each input.”
“SNIP (Meidani et al., 2024), a contrastive pre-training model inspired by CLIP, advances LSO by introducing a multi-modal approach: aligning symbolic and numeric encoders in a shared latent space to l…”
“This paper reframes annotation as a measurement process and introduces a statistical framework for decomposing labeling outcomes into interpretable sources of variation: instance difficulty, annotator…”
“In this paper, we propose a Newton-Schulz-based Riemannian Gradient Scheme (NS-RGS) for orthogonal group synchronization that significantly reduces computational cost by replacing the SVD or QR step w…”
“In symmetric binary Gaussian mixtures, the criterion recovers the critical diffusion time detected by the midpoint derivative of the score and agrees with the spectral criterion of Biroli, Bonnaire, d…”
“Did you read the Ronan Farrow piece in The New Yorker about Sam Altman?”
“https://about.fb.com/news/2024/08/why-europe-should-embrace-open-source-ai-zuckerberg-ek”
“# Open Source AI is the Path Forward”
“We propose MM-WebAgent, a hierarchical agentic framework for multimodal webpage generation that coordinates AIGC-based element generation through hierarchical planning and iterative self-reflection.”
“We propose a new perspective on policy optimization: rather than reweighting all samples by their importance ratios, an optimizer should select which samples are trustworthy enough to drive a policy u…”
“We introduce IRS (Incongruity-Resolution Supervision), a framework that decomposes humor understanding into three components”
“so I have a new essay in the new Atlantis called the new new control society which is really about the how the internet is reshaping politics in our civilization”
“Blog post by Occupy Wall Street”
“We introduce DiscoTrace, a method to identify the rhetorical strategies that answerers use when responding to information-seeking questions.”
“In this paper, we propose K-Token Merging, a latent-space compression framework that merges each contiguous block of K token embeddings into a single embedding via a lightweight encoder.”
“Hence, this paper proposes LArge Scale Small ODE (LASS)-ODE-Power, a learning framework for general-purpose time-domain prediction.”
“In this work, we present QuantCode-Bench, a benchmark for the systematic evaluation of modern LLMs in generating strategies for the Backtrader framework from textual descriptions in English.”
“We propose SpecGuard, a verification-aware speculative decoding framework that performs step-level verification using only model-internal signals.”
“In this work, we propose XQ-MEval, a semi-automatically built dataset covering nine translation directions, to benchmark translation metrics.”
“To address this limitation, we introduce DynAfford, a benchmark that evaluates embodied agents in dynamic environments where object affordances may change over time and are not specified in the instru…”
“Hence, we contribute a comprehensive dataset, \system, comprising scientific architecture images, their corresponding textual descriptions, and associated DOT code representations.”
“Moving beyond this, we propose \textit{IE-as-Cache}, a framework that repurposes IE as a cognitive cache to enhance agentic reasoning.”
“We address this issue by introducing ConfGuide, a novel LtG approach that generates more succinct and targeted guidance. To this end, it employs conformal risk control to select a set of outcomes, ens…”
“In this paper, we present a hybrid approach that combines Large Language Models (LLMs) with three newly created and curated vocabularies to detect and explain hate speech in English, French, and Greek…”
“This paper introduces the LLM fallacy, a cognitive attribution error in which individuals misinterpret LLM-assisted outputs as evidence of their own independent competence, producing a systematic dive…”
“In this paper, we recast LLM unlearning as an asymmetric two-task problem: retention is the primary objective and forgetting is an auxiliary.”
“We propose RACER (Retrieval-Augmented Contextual Rapid Speculative Decoding), a lightweight and training-free method that integrates retrieved exact patterns with logit-driven future cues. This unific…”
“We introduce ClimateCause, a manually expert-annotated dataset of higher-order causal structures from science-for-policy climate reports, including implicit and nested causality. Cause-effect expressi…”
“To address these issues, we propose Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge (CURaTE).”
“We introduce MedImageEdu, a benchmark for multi-turn, evidence-grounded radiology patient education. Each case provides a radiology report with report text and case images.”
“In this comment, we show that the model introduced in Hess et al. Phys. Rev. Lett. {\bf 130}, 207001 (2023) fails the topological gap protocol (TGP)”
“fails the topological gap protocol (TGP) (Pikulin et al., arXiv:2103.12217”
“So the TLDR is that these two papers drastically reduced the potential resources required to run an algorithm, what is called Shor's algorithm.”
“In this work, we propose Clinical Uncertainty Risk Alignment (CURA), a framework that aligns clinical LM-based risk estimates and uncertainty with both individual error likelihoods and cohort-level am…”
“In this work, we propose a novel framework for efficient model aggregation called the early-stopped aggregation (ESA)”
“We propose Generative Augmented Inference (GAI), a general framework that incorporates AI-generated outputs as informative features for estimating models of human-labeled outcomes.”
“To reconnect these approaches, this state-of-the-art survey provides a structured perspective that maps existing XAI techniques onto the various stages of surrogate modeling workflows for design and e…”
“Our method, which is called Batched Robust iHMM (BR-iHMM), balances adaptivity and robustness with two additional tunable parameters. Across limit order book data, hourly electricity demand, and a syn…”
“M. Aghaee et al., Phys. Rev. B 107, 245424 (2023)”
“To resolve this, we propose HiP-LoRA, a spectrum-aware adaptation framework. ... Experiments on Llama-3.1-8B demonstrate that under matched budgets, HiP-LoRA drastically reduces pretraining degradatio…”
“Our results are in striking contradiction with the model of J. L. Tallon and J. G. Storey [Phys. Rev. B 107, 054507 (2023)]”
“Dickerson, Esmaeili, Morgenstern and Zhang (2023) denote the combination of these two constraints as doubly constrained fair clustering. They present algorithms whose guarantees depend on the best kno…”
“To address this, we introduce RoMem, a drop-in temporal knowledge graph module for structured memory systems, applicable to agentic memory and beyond.”
“This paper reports an unexpected finding: in a deterministic hyperdimensional computing (HDC) architecture based on Galois-field algebra”
“Two recent manuscripts [arXiv:2502.19560, arXiv:2503.08944] engage with the topological gap protocol and its use in Phys. Rev. B 107, 245423 (2023) and Subsection S4.3 of the Supplementary Information…”
“Two recent manuscripts [arXiv:2502.19560, arXiv:2503.08944] engage with the topological gap protocol and its use in Phys. Rev. B 107, 245423 (2023) and Subsection S4.3 of the Supplementary Information…”
“We uphold the conclusions of Phys. Rev. B 107, 245423 (2023) and Nature 638, 651-655 (2025).”
“We uphold the conclusions of Phys. Rev. B 107, 245423 (2023) and Nature 638, 651-655 (2025).”
“Relax supports R3 (Rollout Routing Replay)~\[1\] for MoE models with only 1.9\% overhead”
“Here we introduce \textbf{Contrastive Reasoning Path Synthesis (CRPS)}, a framework that transforms supervision extraction...”
“We propose using k-sparse autoencoders [Makhzani and Frey, 2013] to directly control sparsity, simplifying tuning and improving the reconstruction-sparsity frontier.”
“I would encourage you to take a look at the research paper that will give you all of the findings they had some interesting results”
“I encourage you to look at the research supercluster enabled this team to dramatically speed up their training times”
“more details about these results can be found in our upcoming paper for the isca conference industry track later this year”
“we are publishing a blog post and paper with more details about code compose that said we are still early in our work in this space so we look forward to sharing more”
“which were proposed in [Berry and Mondragon 1987, Proc. R. Soc. A 412 53)”
“Our proposal can either be viewed as an implementation of the entropy computing paradigm presented in [Nguyen et. al. Communications Physics 1, 411, 8]”
“This guarantee also depends on the currently best algorithm for DS-fair k-center given by Jones, Nguyen and Nguyen (2020).”
“In this paper, we present Stored Embeddings for Efficient Reinforcement Learning (SEER), a simple modification of existing off-policy RL methods, to address these computational and memory requirements…”
“We hope our proposed architecture serves as a reproducible reference for a minimalistic implementation of transformer based video generation models. Samples and code are available at https://wilson1ya…”
“Here we give an extended review of the quasilinear reformulation of the Lovelock gravitational field equations in harmonic gauge presented in 1409.6656 [gr-qc].”
“In this paper we introduce a new attack algorithm called SCAR, designed to fool classifiers of binary images. We show that SCAR significantly outperforms existing L0 attacks applied to the binary sett…”
“Full write-up:”
“Our paper “Exponential Quantum Advantage in Processing Massive Classical Data” proves that quantum machines can solve common machine learning tasks using exponentially less memory than a classical mac…”
“Thanks, Ingrid Fadelli, for this nice article about our recently published paper with @RobertHuangHY and @MSoleimanifar. The paper describes a surprisingly simple protocol for verifying that a many-qu…”
“This one: https://journals.aps.org/prd/pdf/10.1103/PhysRevD.12.3845”
“This paper introduces the User Data Sharing System (UDSS), a platform-agnostic framework designed to facilitate secure, privacy-first PII (Personally Identifiable Information) exchange between device …”
“This paper presents the Spatio-Temporal Transformer for Long Term Forecasting (STT-LTF ), an extended framework that advances beyond purely temporal analysis to integrate spatial context modeling with…”
“We introduced PHASE (PHysically grounded Abstract Social Events), a large dataset of procedurally generated animations, depicting physically simulated two-agent interactions on a 2D surface.”
“I've discussed supply chain attacks, specifically in the context of the Node.js package manager, NPM ecosystem, in this 2022 update.”
“VentureBeat has a very good article explaining what happened to Axios.”
“Fortifying the enterprise: 10 actions to take now for AI-ready cyber resilience”
“There's there's another blog post that um perhaps you know about called the intelligence curse. Yes. Um which uh goes over some of this ground as well which which I recommend people look up.”
“you know we published it in physical review letters and it got a lot of attention and I think we had a little article in Scientific American that was very proud of”
“I hope you read our paper when it's on archive soon”
“this essay called Keep Your Identity Small, I think, by by Paul Graham is his name.”
“By the way, I want to call out Donald J McGraw's 1974 thesis "The Antibiotic Discovery Era" as a crucial source for this part of the video. McGraw somehow got unprecedented access to Eli Lilly's corpo…”
“How to become a supermanager with AI: https://www.lennysnewsletter.com/p/how-to-become-a-supermanager-with”
“How custom GPTs can make you a better manager | Hilary Gridley (Head of Core Product at Whoop): https://www.youtube.com/watch?v=xDMkkOC-EhI”
“In this work, we derive the non-Markovian dynamics between TLS and qubits during a SWAP-like two-qubit gate and the associated average gate fidelity for frequency-tunable Transmon qubits. This gate de…”
“Answering the question of existence of efficient quantum algorithms for NP-hard problems require deep theoretical understanding of the properties of the low-energy eigenstates and long-time coherent d…”
“I just published "Governance, Part 2: Plutocracy Is Still Bad": https://t.co/LTMrsxFeuS”
“you can check out the paper that Michael Nielson had about this idea”
“In this paper, we report the design and characterization of a prototype cryogenic CMOS integrated circuit that has been optimized for the control of transmon qubits. The circuit has been integrated in…”
“Quantum Neural Networks (QNNs) are a promising variational learning paradigm with applications to near-term quantum processors, however they still face some significant challenges.”
“This is an updated version of supplementary information to accompany "Quantum supremacy using a programmable superconducting processor", an article published in the October 24, 2019 issue of Nature. T…”
“Summary of changes since arXiv:1910.11333v1 (submitted 23 Oct 2019)”
“# GLoMo: Unsupervisedly Learned Relational tGraphs as Transferable Representations”
“We introduce a fermion-to-qubit mapping defined on ternary trees, where any single Majorana operator on an $n$-mode fermionic system is mapped to a multi-qubit Pauli operator acting nontrivially on $\…”
“First of all, Center for Humane Technology, my nonprofit, has a solutions report that's coming out around the time of the film. It's a PDF. It has, I think, seven major solutions. I want everybody to …”
“Here we report on experimental observations of relaxation in such simulations, measured on up to 1440 qubits with microsecond resolution. By initializing the system in a state with topological obstruc…”
“According to a new report by Citadel Research, software engineering job postings are rising rapidly.”
“This video is actually very heavily inspired by this article, and I'm going to link to it in the description because I highly recommend that you read the whole thing. It is definitely worth your time.”
“Here my friend Jens Eisert and I assess the current status and the challenges ahead.”
“The paper that blew my mind was InstructGPT, because it pointed out that you can take the pretrained model, which is autocomplete, and if you just fine-tune it on text that looks like conversations, t…”